Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to enhancing comprehension and insights into various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    gaining understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Alternative
    -0.48
    alternative
    -0.47
    Alternative
    -0.46
     Alternate
    -0.43
     alternative
    -0.43
     floor
    -0.43
     trip
    -0.42
    usermodel
    -0.42
     AssemblyVersion
    -0.41
     poule
    -0.41
    POSITIVE LOGITS
     understanding
    0.56
    Understanding
    0.52
     kasarigan
    0.51
     zanahoria
    0.50
     وتسجيلات
    0.49
     enjeux
    0.48
     understood
    0.48
     understand
    0.46
     Understanding
    0.45
     Menschheit
    0.45
    Act Density 0.077%

    No Known Activations